This study addresses the Domain-Class Incremental Learning problem, a realistic but
challenging continual learning scenario where both the domain distribution and target …

Spiking neural networks (SNNs) offer an energy-efficient alternative to conventional deep
learning by emulating the event-driven processing manner of the brain. Incorporating …

Camouflaged Object Detection (COD) refers to the task of identifying and segmenting
objects that blend seamlessly into their surroundings, posing a significant challenge for …

Real-world Image Dehazing (RID) aims to alleviate haze-induced degradation in real-world
settings. This task remains challenging due to the complexities in accurately modeling real …

Achieving a lower radiation dose and a faster imaging speed is a pivotal objective of
computed tomography (CT) reconstruction. However, these often come at the cost of …

Recently, token-based generation have demonstrated their effectiveness in image synthesis.
As a representative example, non-autoregressive Transformers (NATs) can generate decent …

As the demand for high-quality training data escalates, researchers have increasingly turned
to generative models to create synthetic data, addressing data scarcity and enabling …

In the domain of computer vision, Parameter-Efficient Tuning (PET) is increasingly replacing
the traditional paradigm of pre-training followed by full fine-tuning. PET is particularly …

Recently, research on denoising diffusion models has expanded its application to the field of
image restoration. Traditional diffusion-based image restoration methods utilize degraded …